1.1.0
This version add new features:
InvertibleDownSampling
andInvertibleUpSampling
- multiclass extension of the HKR loss
It also contains the multiple fixes for:
- bug with
L2NormPooling
- bug with
vanilla_export
- bug with
tf.function
annotation causing incorrect Lipschitz constant inSequential
(for constant others than 1).
Breaking changes:
- the
true_values
parameter has been removed in binary HKR as both (1, -1) and (1,0) are handled automatically.